whatmodel.sh / MiMo-V2-Omni
MiMo-V2-Omni
↗ share
+ contribute
MiMo-V2-Omni is a closed-weights language model from Xiaomi, released March 2026.
Catalogue identity notes
Comparison-only. Arena entry 'mimo-v2-omni' (xiaomi, Proprietary), first listed 2026-05-01 (vision). Not MiMo-V2.5.
Model information sources
$ how it compares
The LLMs ranked either side of MiMo-V2-Omni, out of 828 with a score, then more from Xiaomi.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 115 |  Step 3.5 Flash (196B-A11B) | 68±1 | api $0.15/M +local | ||
| 116 |  DeepSeek V3.2 | 68±1 | api $0.29/M +local | ||
| 117 | MiMo-V2-Omni | 68±2 | comparison only | ||
| 118 |  Gemini 2.5 Pro Experimental (03-25) | 68±3 | comparison only | ||
| 119 |  Grok 4 (0709) | 68±1 | comparison only | ||
| more from Xiaomi | |||||
| 15 | MiMo-V2.6-Pro | 79±1 | api $0.54/M +local | ||
| 27 | MiMo-V2.6-Flash (309B-A15B) | 77±1 | api $0.17/M +local | ||
| 91 | MiMo-V2-Pro | 70±1 | comparison only | ||
$ what it's good at
chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #86 of 463 * · 30% of its score · 1 test
Beats LongCat 2.0 (1.6T-A48B), Mistral Large 4 (public preview), Inkling Small (266B-A12B) here, though they rank higher overall. Trails Gemma 4 12B, Gemma 4 26B-A4B, Nemotron Cascade 2 30B-A3B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1431.0 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 286/379 | 30% |
vision & documents▁▁▃▃▂▃▅▄▇▇█▃ #73 of 182 · 68% of its score · 4 tests
Beats DeepSeek V4 Flash Vision (Exp), GPT-5, Inkling Small (266B-A12B) here, though they rank higher overall. Trails Gemma 4 26B-A4B, Claude Haiku 4.5, Qwen3.6 Flash here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| CharXiv (reasoning questions) lab +1 | 80.1% ✎ | ▂▅▃▅▅▆▆▅▆█▆▂ beats 76/100 | 22% |
| Arena vision (style controlled) | 1216.1 ✎ | ▁▁▂▂▂▂▄▅▅▆██ beats 82/145 | 21% |
| ChartArena chart parsing (English, mAP_high average) | 43.9% ✎ | ▁·▁·▃▃▁▇▃█·▄ beats 15/22 | 17% |
| MMMU Pro lab | 76.8% ✎ | ▂▃▁▃▆▇▃▇▇██▅ beats 43/52 | 9.1% |
other tests3 not in a task · 0.0% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| HR-Bench 4K lab | 83.3% ✎ | █··········█ beats 0/1 | — |
| Daily-Omni lab | 80.5% ✎ | █··········█ beats 0/1 | — |
| Video-Holmes lab | 59.5% ✎ | █··········█ beats 0/1 | — |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · LMArena leaderboard dataset 51%, XiaomiMiMo/MiMo-V2.5 model ca… 20%, ChartArena: Benchmarking Char… 17% and 1 more
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 LMArena leaderboard dataset | 2 | 51% |
 XiaomiMiMo/MiMo-V2.5 model card · lab-reported | 2 | 20% |
 ChartArena: Benchmarking Chart Parsing across Languages, Scenarios, and Formats (arXiv:2606.01348v3) | 1 | 17% |
 Xiaomi MiMo vendor-reported benchmark scores for its own models (mimo.xiaomi.com launch pages) · lab-reported | 1 | 11% |
| prior · pull toward the middle | 2% | |
| weighted average | = 68.1 |
not counted (3)
| XiaomiMiMo/MiMo-V2.5 model card | HR-Bench 4K [correct] | 83.3% | fewer than three models have this test yet, or this source ran it for this model alone |
| XiaomiMiMo/MiMo-V2.5 model card | Daily-Omni [correct] | 80.5% | fewer than three models have this test yet, or this source ran it for this model alone |
| XiaomiMiMo/MiMo-V2.5 model card | Video-Holmes [correct] | 59.5% | fewer than three models have this test yet, or this source ran it for this model alone |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json